Claude Dynamic Workflows Codex

Claude Dynamic Workflows — on Codex

A **Claude Code skill**: type `/codex-workflows ` and a fleet of **Codex (GPT) agents** fans out across the work — Claude authors the workflow, runs it on your local `codex app-server`, and streams it back as a live **execution map**.

[](LICENSE)   [](https://github.com/scasella/claude-dynamic-workflows-codex/actions/workflows/ci.yml)


↑ a real run: diagnose a checkout latency regression — triage the signals in parallel, **race three root-cause workers** and cancel the losers, steer the winner on its warm thread, then gate the fix. This is the bundled demo; open it yourself in 10 seconds ([below ↓](#see-it-now-no-codex-required)).

You describe a task; Claude Code writes a [dynamic-workflow](https://code.claude.com/docs/en/workflows) script — `agent()` / `parallel()` / `pipeline()` / `phase()` / `budget` — and runs it across dozens of GPT-5 agents instead of Claude subagents. The runtime holds the loop, branching, and intermediate results, so your context only sees the final answer — and you watch it build as an interactive map. And unlike the native one-shot DSL, workers here can stay **live** — steer a worker on warm context, race several and cancel the losers, or let a controller adapt the plan as results land ([Beyond one-shot ↓](#beyond-one-shot-sessionful-workers)). It scales one level up, too: add **`--multi`** and Claude launches a whole **fleet of concurrent workflows and supervises them itself** — answering their gates, steering, killing dead ends, forking winners ([walkthrough 8 ↓](#8--run-a-whole-fleet--and-let-claude-supervise-it)). Great for codebase a